Intelligent control system for paint spraying process

Abstract

The invention relates to the technical field of automatic control, in particular to a paint spraying process intelligent control system which comprises an airflow dynamic monitoring module, an entropy optimization regulation and control module, an acoustic quality monitoring module and a visual precision correction module. According to the invention, through the integration of real-time monitoring and regulation and control technologies, the quality and efficiency of the paint spraying process are obviously optimized, the real-time adjustment of spraying parameters is realized by using fine airflow and particle behavior data, the paint is ensured to be uniformly distributed, the material waste is greatly reduced, the thickness and uniformity of a coating can be accurately evaluated through the analysis of sound wave signals, and the real-time monitoring and control of the paint spraying process are realized. The quality deviation is timely found and corrected, the coating quality is improved, the heavy work and rejection rate are reduced, the overall production efficiency is improved, meanwhile, the spraying process is accurately corrected through real-time image analysis, it is ensured that each step of operation is executed under the optimal condition, and the high-quality and high-efficiency spraying result is achieved.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to an intelligent control system for a paint spraying process. Background Art

[0002] The field of automation control technology covers a wide range of applications, mainly focusing on the use of computer systems, sensors, controllers and software algorithms to manage and optimize mechanical and industrial processes. The core is to improve the efficiency, accuracy and repeatability of the system while reducing labor costs and operational errors. Automation control systems are widely used in many fields such as manufacturing, logistics, transportation, energy management, and home and office automation. From simple timing control to the evolution of complex real-time feedback and adaptive control strategies, artificial intelligence and machine learning technologies are generally integrated to further enhance the intelligence level and decision-making ability of the system.

[0003] Among them, the intelligent control system of paint spraying process refers to a specific automation technology application used to control and optimize the paint spraying process. The system monitors and adjusts the spraying parameters (such as nozzle speed, pressure, spraying angle and paint flow) through integrated sensors to ensure uniform distribution of paint and optimization of drying time. Its main purpose is to improve the quality and efficiency of paint operations, reduce material waste, and ensure the safety of the working environment.

[0004] Existing technologies in the field of paint spraying have not yet widely integrated real-time feedback and adaptive control technologies. They usually rely on preset operating parameters and lack the ability to respond to changes in environmental variables in real time. This limitation results in the system being unable to adjust immediately when encountering changes in airflow or material properties, which can easily cause uneven spraying or material waste, and may even lead to safety hazards. Traditional quality control methods mostly rely on manual inspection or simple automated equipment, which makes it difficult to achieve precise control and timely adjustment of coating quality, affecting production efficiency and cost control, while also limiting the sustainability of the production process and the satisfaction of environmental standards. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent control system for a paint spraying process.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: an intelligent control system for a paint spraying process comprises: The airflow dynamic monitoring module monitors the air flow speed and direction in the spraying environment, collects the distribution information of paint particles in the air, calculates the paint particle distribution density in the spraying area based on the collected information, analyzes the paint particle behavior, and constructs a paint particle spraying density distribution map; The entropy value optimization control module analyzes the current state of the nozzle and adjusts the paint flow rate according to the paint particle spraying density distribution map, adjusts the spraying path according to the analysis results, corrects the nozzle angle and flow rate, calculates the spraying efficiency, and generates optimized spraying parameters; The acoustic quality monitoring module controls the nozzle by optimizing the spraying parameters, collects the acoustic wave signal during the spraying process, analyzes the change of the acoustic wave signal, analyzes the thickness and uniformity of the paint coating according to the analysis results, performs quality assessment, and generates acoustic diagnosis results; The visual precision correction module uses a camera to collect images of the coating after spraying, adjusts the spraying parameters in combination with the acoustic diagnosis results to correct deviations, updates the spraying strategy in real time, and generates an intelligent control solution for the paint spraying process.

[0007] As a further solution of the present invention, the step of collecting the distribution information of the paint particles in the air is: Sensors are deployed at key locations in the spraying area to record the air flow speed and direction in real time, using the air flow rate calculation formula.

[0008] Generates a real-time record of airflow speed and direction, where Indicates the air velocity, Indicates the distance the airflow moves. Indicates time, Represents the adjustment coefficient, which is used to adjust the periodic fluctuations of air flow. represents the angular frequency, which represents the rate of periodic fluctuations, represents the phase, which indicates the initial angle of the periodic fluctuation; Based on the real-time recording of the airflow speed and direction, the data is analyzed to calculate the vectorized airflow speed and direction, using the formula,

[0009] Generates vectorized airflow velocity and direction analysis data, where represents the air flow velocity vector, and are the velocity components of the airflow in the horizontal and vertical directions, and are the attenuation coefficient and time constant, which are used to enhance the model's ability to describe unsteady airflow; Using the analysis data of the vectorized air flow velocity and direction, the distribution information of paint particles in the spraying environment is collected and analyzed, and the formula is applied.

[0010] Calculate the paint particle concentration in any area and generate paint particle air distribution information, where: Indicates at location The paint particle concentration, is the Dirac delta function, which means that at position The response when there are paint particles, It is The position of each paint particle, is the total volume area.

[0011] As a further solution of the present invention, the steps of constructing the paint particle spraying density distribution map are: According to the air distribution information of the paint particles, statistical analysis is performed to calculate the distribution density of the paint particles in the spraying area, and the density estimation formula is used.

[0012] Generates paint particle density analysis data, where represents the particle density, represents the Gaussian kernel function, Indicates The position of each paint particle, represents the bandwidth of the kernel function, represents the total number of particles; Based on the paint particle density analysis data, particle behavior simulation is performed using a simulation formula.

[0013] Generate particle behavior simulation results, where is the net force acting on the particle, is the mass of the particle, is the acceleration of the particle, is the damping coefficient, which is used to adjust the effect of air resistance on the movement of paint particles. In combination with the particle behavior simulation results, data visualization technology is used to draw a paint particle distribution map, and the difference density areas are represented by color depth, and the paint particle spraying density distribution map is output.

[0014] As a further solution of the present invention, the steps of analyzing the current state of the nozzle and adjusting the paint flow rate are: According to the paint particle spraying density distribution diagram, the mean value of the regional density is calculated using the formula:

[0015] Get the average density data, where It is The density value of the area, It is The weight coefficient of the region represents the size or importance of the region. Indicates the total number of regions, represents the weighted average density; Based on the average density data, calculate the standard deviation to assess the current uniformity of the nozzle using the formula,

[0016] Generate density deviation data to reflect the uniformity of the spraying process, where represents the weighted density deviation, Indicates The density value of the area, represents the weighted average density, It is The weight coefficient of the region, Indicates the total number of regions; Using the density deviation data, adjust the paint flow rate using the formula,

[0017] The adjusted paint flow data is calculated, where: represents the adjusted paint flow, Represents the basic flow, represents the weighted density deviation, represents the base density deviation, Represents the sensitivity adjustment factor, which is used to optimize the accuracy of the calculation. represents the natural exponential function.

[0018] As a further solution of the present invention, the step of obtaining the optimized spraying parameters is: According to the adjusted paint flow data, calculate the basic flow The difference between

[0019] Generate traffic difference data, where Represents the difference in flow before and after. represents the adjusted paint flow, Represents basic traffic; Based on the flow difference data, the nozzle angle is adjusted to match the new flow demand, using the formula,

[0020] Generate new nozzle angle parameters, where represents the new nozzle angle, represents the original nozzle angle, represents the angle adjustment factor, which is used to adjust the sensitivity of nozzle angle changes; According to the new nozzle angle parameters and the adjusted paint flow data, the formula is used:

[0021] Calculate the expected spraying efficiency and output the optimized spraying parameters, where: Represents the adjusted spraying efficiency, Represents the adjusted traffic data, represents the new nozzle angle parameter, Represents the estimated spraying area.

[0022] As a further solution of the present invention, the analysis steps of the sound wave signal change are: According to the optimized spraying parameters, combined with the actual conditions, adjust the operating parameters of the nozzle, using the formula,

[0023] Generate adjusted nozzle control parameters; where, and They are demand and current spray flow, Indicates the deviation from the target pressure, is the target pressure, is the adjustment index, which is used to enhance the sensitivity of the adjustment process. represents the optimized spraying parameters; Based on the adjusted nozzle control parameters, a microphone is used to collect the acoustic wave signal, and the formula is used:

[0024] Perform signal processing to generate sound wave signal analysis results, where: and are the time-dependent amplitude and phase changes, respectively, is the fundamental frequency, is a random noise term, A time series representing an acoustic signal; According to the acoustic signal analysis results, a deep analysis is performed using the formula:

[0025] Analyze the key features in the spectrum, calculate the spectrum distribution, and obtain the analysis results of the sound wave signal changes, among which, represents the frequency spectrum of the sound wave signal, Represents the angular frequency.

[0026] As a further solution of the present invention, the steps of obtaining the acoustic diagnosis result are: Based on the analysis results of the acoustic wave signal changes, the coating thickness is calculated using the formula:

[0027] Output coating thickness data, where is the material attenuation coefficient, is the maximum amplitude of the spectrum, is the reference amplitude, is the calibration constant, Indicates the coating thickness value; The coating thickness data was analyzed and the statistical distribution was evaluated using the formula,

[0028] Calculate the coating uniformity and obtain the coating uniformity analysis results, where: Indicates the coating uniformity evaluation value, Indicates the coating thickness at the measuring point, represents the average coating thickness, Indicates the number of measurement points; The coating uniformity analysis results were compared with industry standards for quality assessment using the formula,

[0029] Generate acoustic diagnostic results ,in, is the quality rating coefficient, is the maximum allowable uniformity value.

[0030] As a further solution of the present invention, the steps for obtaining the intelligent control solution of the paint spraying process are: The camera is used to capture the coating image after spraying in real time, and the enhanced image acquisition formula is used.

[0031] Generate a preliminary coating image dataset, where Representative time The image data at that time, cs represents the camera setting parameter value, represents exposure time, L represents lighting intensity, and p represents environmental factors. is a normalization constant to ensure the rationality of the data; Apply deep learning image analysis techniques to the preliminary coating image dataset to extract key features of coating quality, using the formula,

[0032] Get the coating quality feature set, where is the average value of the image data, is the total number of pixels, Represents the image quality characteristic value; Based on the coating quality feature set and acoustic diagnosis results, the spraying parameters are dynamically adjusted, and the formula is applied.

[0033] Generate feedback-adjusted spray parameters, where Represents the reference value of the new spraying parameters, is the reference value of the current spraying parameters, Indicates the acoustic diagnosis result, is the adjustment factor used to enhance the calculation accuracy; Apply the feedback-adjusted spraying parameters, continuously monitor the spraying effect, integrate all monitoring data, update the spraying strategy, and output an intelligent control solution for the paint spraying process.

[0034] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the quality and efficiency of the paint spraying process are significantly optimized through the integration of real-time monitoring and control technologies. The precise airflow and particle behavior data are used to achieve real-time adjustment of the spraying parameters, ensure uniform distribution of the paint, and greatly reduce material waste. The analysis of the acoustic wave signal can accurately evaluate the thickness and uniformity of the coating, and timely detect and correct quality deviations, which not only improves the coating quality, reduces rework and scrap rates, and improves overall production efficiency, but also accurately corrects the spraying process through real-time image analysis to ensure that each step of the operation is performed under optimal conditions, achieving high-quality and high-efficiency spraying results. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a system flow chart of the present invention; Figure 2 A flow chart for collecting the distribution information of paint particles in the air of the present invention; Figure 3 A flow chart for constructing a paint particle spraying density distribution diagram of the present invention; Figure 4 A flowchart for analyzing the current state of the nozzle and adjusting the paint flow rate according to the present invention; Figure 5 A flow chart for obtaining the optimized spraying parameters of the present invention; Figure 6 It is a flow chart of analyzing the change of the acoustic wave signal of the present invention; Figure 7 A flowchart for obtaining acoustic diagnosis results of the present invention; Figure 8 The figure is a flow chart for obtaining the intelligent control scheme for the paint spraying process of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0037] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0038] See also Figure 1 , an intelligent control system for a paint spraying process includes: The airflow dynamic monitoring module monitors the air flow speed and direction in the spraying environment, collects the distribution information of paint particles in the air, calculates the paint particle distribution density in the spraying area based on the collected information, analyzes the paint particle behavior, and constructs a paint particle spraying density distribution map; The entropy optimization control module analyzes the current state of the nozzle and adjusts the paint flow rate according to the paint particle spray density distribution map. It adjusts the spray path according to the analysis results, corrects the nozzle angle and flow rate, calculates the spray efficiency, and generates optimized spray parameters. The acoustic quality monitoring module controls the nozzle by optimizing the spraying parameters, collects the acoustic wave signals during the spraying process, analyzes the changes in the acoustic wave signals, analyzes the thickness and uniformity of the paint coating based on the analysis results, conducts quality assessment, and generates acoustic diagnosis results; The visual precision correction module uses a camera to capture images of the coating after spraying, adjusts the spraying parameters based on the acoustic diagnosis results to correct deviations, updates the spraying strategy in real time, and generates an intelligent control solution for the paint spraying process.

[0039] The dynamic data of airflow include speed index, direction index and distribution density index; the optimized spraying parameters include nozzle angle setting results, flow configuration results and spraying path optimization results; the acoustic diagnosis results include sound wave characteristic analysis results, coating thickness data and coating uniformity data; the intelligent control scheme of paint spraying process includes spraying strategy adjustment measures, parameter adjustment suggestions and quality control report.

[0040] See also Figure 2 , the steps to collect the distribution information of paint particles in the air are: Sensors are deployed at key locations in the spraying area to record the air flow speed and direction in real time, using the air flow rate calculation formula.

[0041] Generates a real-time record of airflow speed and direction, where Indicates the air velocity, Indicates the distance the airflow moves. Indicates time, Represents the adjustment coefficient, which is used to adjust the periodic fluctuations of air flow. represents the angular frequency, which represents the rate of periodic fluctuations, represents the phase, which indicates the initial angle of the periodic fluctuation; Based on the real-time recording of airflow speed and direction, the data is analyzed to calculate the vectorized airflow speed and direction, using the formula,

[0042] Generates vectorized airflow velocity and direction analysis data, where represents the air flow velocity vector, and are the velocity components of the airflow in the horizontal and vertical directions, and are the attenuation coefficient and time constant, which are used to enhance the model's ability to describe unsteady airflow; Using vectorized air flow velocity and direction analysis data, we collect and analyze the distribution information of paint particles in the spraying environment, and apply the formula.

[0043] Calculate the paint particle concentration in any area and generate paint particle air distribution information, where: Indicates at location The paint particle concentration, is the Dirac delta function, which means that at position The response when there are paint particles, It is The position of each paint particle, is the total volume area.

[0044] Assume that in a measurement process, the airflow is measured to move 9 meters in 3 seconds. Considering that the airflow may have periodic changes, the adjustment coefficient is set m / s, angular frequency Radians / second, Phase radian.

[0045] Calculate the base flow rate:

[0046] Calculate the cyclical fluctuation contribution:

[0047] Substituting specific numbers:

[0048] Comprehensive flow rate calculation:

[0049] The flow rate obtained It means that after considering the periodic fluctuation of airflow, the actual average airflow velocity is meters, which can more accurately describe the dynamic behavior of air in the spraying area.

[0050] Assume that the air flow velocity obtained from step 1 is m / s, Meters / second. Set the attenuation coefficient m / s, time constant Seconds, in Calculate the attenuation contribution at 1 second, then: Calculate the attenuation term:

[0051] Resulting vector velocity:

[0052] Calculation results of vectorized air velocity The main velocity in the horizontal direction and the smaller velocity component in the vertical direction are shown, as well as additional velocity contributions that decay very little with time, which helps to describe and analyze the airflow dynamics in the spray environment in more detail.

[0053] Assume that in a volume The position is detected by image analysis technology within the control area of ​​​​the cubic meter rice, There is a paint particle at each meter.

[0054] Apply the delta function to calculate the contribution of each particle: The delta function is equal The value is 1 at this time and 0 at other times.

[0055] calculate and Particle concentration:

[0056]

[0057] Concentration calculation results and It shows that at these two locations, there is one paint particle per cubic meter of space, which provides quantitative information on the distribution of paint particles in the spraying area, which is helpful for further analysis of paint particle behavior and optimization of the spraying process.

[0058] See also Figure 3 , the steps to construct the paint particle spray density distribution map are: According to the air distribution information of paint particles, statistical analysis is performed to calculate the distribution density of paint particles in the spraying area, and the density estimation formula is used.

[0059] Generates paint particle density analysis data, where represents the particle density, represents the Gaussian kernel function, Indicates The position of each paint particle, represents the bandwidth of the kernel function, represents the total number of particles; Based on the paint particle density analysis data, particle behavior simulation is performed using simulation formulas.

[0060] Generate particle behavior simulation results, where is the net force acting on the particle, is the mass of the particle, is the acceleration of the particle, is the damping coefficient, which is used to adjust the effect of air resistance on the movement of paint particles. Combined with the particle behavior simulation results, data visualization technology is used to draw a paint particle distribution map, and the difference in density areas is represented by color depth, and the paint particle spraying density distribution map is output.

[0061] Assume that in a given area, the position of the paint particles is rice, Meters, set the kernel function bandwidth m, using Gaussian kernel function for density estimation.

[0062] Calculate the impact of the kernel function: for The contribution of each particle is calculated using the Gaussian kernel function:

[0063]

[0064] Calculate the total density:

[0065] Calculated density Particles / meter, expressed in The paint particle density at the meter position is 2.419 particles per meter. The value indicates the degree of paint particle aggregation at this position, which helps to determine the quality and uniformity of spraying.

[0066] Assume that the mass of a particle is Grams (converted to kilograms kg), estimate the particle acceleration due to airflow rice / The resultant force, taking into account the damping coefficient Newton second / meter, particle speed m / s (obtained from the previous calculation).

[0067] Substitute into the formula and calculate:

[0068] The combined force obtained Newton showed that under such airflow and damping conditions, the paint particles are subject to a force that supports their rapid movement. The magnitude of this force helps to simulate the behavior of particles during the spraying process, thereby predicting and optimizing the spraying effect.

[0069] Using the particle behavior simulation results and combined with the particle density data, use 3D graphics software (such as MATLAB or Python's matplotlib) to plot the density of each paint particle position. The color depth represents the density, and finally output the paint particle spray density distribution map.

[0070] See also Figure 4 , the execution steps to analyze the current status of the nozzle and adjust the paint flow are: According to the paint particle spray density distribution map, calculate the mean of the regional density using the formula,

[0071] Get the average density data, where It is The density value of the area, It is The weight coefficient of the region represents the size or importance of the region. Indicates the total number of regions, represents the weighted average density; Based on the average density data, calculate the standard deviation to evaluate the current uniformity of the nozzle, using the formula,

[0072] Generate density deviation data to reflect the uniformity of the spraying process, where represents the weighted density deviation, Indicates The density value of the area, represents the weighted average density, It is The weight coefficient of the region, Indicates the total number of regions; Using density deviation data, adjust the paint flow rate, using the formula,

[0073] The adjusted paint flow data is calculated, where: represents the adjusted paint flow, Represents the basic flow, represents the weighted density deviation, represents the base density deviation, Represents the sensitivity adjustment factor, which is used to optimize the accuracy of the calculation. represents the natural exponential function.

[0074] Suppose there are three regions with density They are , the corresponding weight for . Calculate the weighted average density:

[0075]

[0076]

[0077] The calculated average density is , this value represents the average paint density of the entire spraying area taking into account the area weight, which helps to evaluate whether the nozzle distributes the paint evenly.

[0078] Continue using the previous calculation results :

[0080]

[0081]

[0082] Density deviation for , indicating the degree of deviation of the oil slurry density from the average value during the spraying process. A higher value indicates a more even spray.

[0083] Assumptions , reference density deviation , combined with the above calculation results, we get:

[0084]

[0085] Adjusted paint flow for , which shows that in order to cope with density deviation and maintain spray uniformity, the paint flow rate needs to be increased by 10%.

[0086] See also Figure 5 , the steps to obtain the optimized spraying parameters are: According to the adjusted paint flow data, calculate the basic flow The difference between

[0087] Generate traffic difference data, where Represents the difference in flow before and after. represents the adjusted paint flow, Represents basic traffic; Based on the flow difference data, adjust the nozzle angle to match the new flow demand, using the formula,

[0088] Generate new nozzle angle parameters, where represents the new nozzle angle, represents the original nozzle angle, represents the angle adjustment factor, which is used to adjust the sensitivity of nozzle angle changes; According to the new nozzle angle parameters and the adjusted paint flow data, the formula is used.

[0089] Calculate the expected spraying efficiency and output the optimized spraying parameters, where: Represents the adjusted spraying efficiency, Represents the adjusted traffic data, represents the new nozzle angle parameter, Represents the estimated spraying area.

[0090] Continue using the previous calculation results , assuming , substituting into the formula, we get:

[0091] Traffic Difference for , indicating that in order to achieve a more uniform spraying effect, the paint flow rate needs to be increased .

[0092] Assuming the original nozzle angle , adjustment coefficient ,but:

[0093]

[0094] New nozzle angle At 45.0085 degrees, minimal adjustments are required to accommodate increased flow and maintain even spraying.

[0095] Assuming the expected spraying area :

[0096]

[0097] Adjusted spraying efficiency for , indicating the efficiency of the required amount of paint per square meter under the new angle adjustment. This value helps determine the paint consumption and efficiency of the spraying operation, ensuring the optimal use of resources.

[0098] See also Figure 6 , the analysis steps of the acoustic signal change are: According to the optimized spraying parameters, combined with the actual conditions, adjust the operating parameters of the nozzle, use the formula,

[0099] Generate adjusted nozzle control parameters; where, and They are demand and current spray flow, Indicates the deviation from the target pressure, is the target pressure, is the adjustment index, which is used to enhance the sensitivity of the adjustment process. Represents optimized spraying parameters; Based on the adjusted nozzle control parameters, a microphone is used to collect the acoustic wave signal, and the formula is used.

[0100] Perform signal processing to generate sound wave signal analysis results, where: and are the time-dependent amplitude and phase changes, respectively, is the fundamental frequency, is a random noise term, A time series representing an acoustic signal; According to the results of the acoustic signal analysis, a deep analysis is performed using the formula:

[0101] Analyze the key features in the spectrum, calculate the spectrum distribution, and obtain the analysis results of the sound wave signal changes, among which, represents the frequency spectrum of the sound wave signal, Represents the angular frequency.

[0102] Assumptions: : Demand flow, set to .

[0103] : Current flow, set to .

[0104] : Pressure deviation, the difference between the current and target pressures, assumed to be 5psi.

[0105] : Target pressure, set to 20psi.

[0106] : Adjust the exponent, set to 2.

[0107] Calculate the base pressure adjustment ratio:

[0108] Calculate the pressure deviation factor:

[0109] Apply the adjustment index:

[0110] Calculate the final control parameters:

[0111] The adjusted nozzle control pressure is obtained It is about 22psi, which means that in order to meet the required standards, the nozzle pressure needs to be increased from 20psi to about 22psi.

[0112] Assumptions: : Amplitude, assumed to be a function .

[0113] : Phase, assuming .

[0114] : Basic frequency, assumed to be .

[0115] : Noise term, assumed to be random noise, with a mean of 0 and a standard deviation of 0.5.

[0116] exist Seconds: Calculate the amplitude: 0.087 calculate part:

[0117] Add noise: (Random value) Calculate the signal:

[0118] exist Seconds, the recorded sound wave signal strength Approx. This value reflects the amplitude of the sound wave during the spraying process at one second, taking into account noise interference.

[0119] : angular frequency, considering The corresponding angular frequency .

[0120] : The signal obtained in the previous step, simplify the calculation, use , representing a periodic sound wave signal.

[0121] calculate exist The value at time. It is a simple cosine wave, and the Fourier transform can be directly calculated. For the Fourier transform of the cosine wave, the result will be concentrated at the frequency of the cosine wave, and the contribution of other frequencies will be zero. The standard result of the Fourier transform of the cosine wave is:

[0122] in, is the amplitude, is the fundamental frequency of the signal, is the Dirac delta function, which represents the concentration of the spectrum at a specific frequency.

[0123] Substitute the actual parameters into:

[0124]

[0125] This calculation shows that the signal Spectrum exist There is a peak at , and the intensity of the peak is The results indicate that the acoustic signal is There is a significant concentration of energy at this point, which may be related to a specific acoustic vibration mode caused by the nozzle operating parameters. The intensity of this frequency may affect the application effect of the coating and is directly related to the thickness and uniformity of the coating.

[0126] See also Figure 7 , the steps to obtain the acoustic diagnosis results are: Based on the analysis results of the acoustic wave signal changes, the coating thickness is calculated using the formula:

[0127] Output coating thickness data, where is the material attenuation coefficient, is the maximum amplitude of the spectrum, is the reference amplitude, is the calibration constant, Indicates the coating thickness value; Analyze coating thickness data and evaluate statistical distribution using formulas,

[0128] Calculate the coating uniformity and obtain the coating uniformity analysis results, where: Indicates the coating uniformity evaluation value, Indicates the coating thickness at the measuring point, represents the average coating thickness, Indicates the number of measurement points; Compare the coating uniformity analysis results with industry standards for quality assessment, using the formula,

[0129] Generate acoustic diagnostic results ,in, is the quality rating coefficient, is the maximum allowable uniformity value.

[0130] Assume the following data exists: : Material specific attenuation coefficient, this parameter affects the calculation of coating thickness, assumed to be 0.1.

[0131] : The maximum amplitude value obtained from the spectrum analysis in step 3, assumed to be .

[0132] : Reference amplitude, set to a standard value, set to 1.0.

[0133] : Calibration constant, used to adjust the calculation deviation, set to 0.1.

[0134] Calculate the amplitude ratio:

[0135] Apply the decay coefficient and logarithmic function:

[0136] Calculate coating thickness:

[0137] result Indicates that under the current test conditions and settings, the calculated coating thickness is about This thickness value is interpreted from the acoustic spectrum data and shows the physical properties of the coating in actual application.

[0138] Assume there are 4 groups of measuring points, the coating thickness at each measuring point is , respectively .

[0139] The average coating thickness is:

[0140] Calculate the variance:

[0141]

[0142] Calculate the standard deviation:

[0143] The standard deviation obtained , which is an indicator for evaluating coating uniformity, a smaller value indicates that the coating thickness is relatively uniform, which can be regarded as a good uniformity level compared with industry standards.

[0144] : Quality rating coefficient, set to 100, indicating the maximum rating value.

[0145] : The uniformity standard deviation obtained by the above calculation is .

[0146] : Maximum allowable uniformity value, set to , indicating the maximum tolerated deviation from the industry standard.

[0147] Calculate the uniformity ratio:

[0148] Calculate the final diagnostic score:

[0149] Acoustic diagnostic score obtained , the score indicates that the quality of the coating is above average, but there is room for improvement.

[0150] See also Figure 8 , the steps to obtain the intelligent control solution of the paint spraying process are: The camera is used to capture the coating image after spraying in real time, and the enhanced image acquisition formula is used.

[0151] Generate a preliminary coating image dataset, where Representative time The image data at that time, cs represents the camera setting parameter value, represents exposure time, L represents lighting intensity, and p represents environmental factors. is a normalization constant to ensure the rationality of the data; Apply deep learning image analysis techniques to the preliminary coating image dataset to extract key features of coating quality, using the formula,

[0152] Get the coating quality feature set, where is the average value of the image data, is the total number of pixels, Represents the image quality characteristic value; Based on the coating quality feature set and acoustic diagnosis results, the spraying parameters are dynamically adjusted, and the formula is applied.

[0153] Generate feedback-adjusted spray parameters, where Represents the reference value of the new spraying parameters, is the reference value of the current spraying parameters, Indicates the acoustic diagnosis result, is the adjustment factor used to enhance the calculation accuracy; The application feedback adjusts the spraying parameters, continuously monitors the spraying effect, integrates all monitoring data, updates the spraying strategy, and outputs the intelligent control plan for the paint spraying process.

[0154] : Normalization constant to ensure that the data range is suitable for the analysis algorithm, assumed to be 100.

[0155] L: Brightness intensity, assumed to be 0.05, unit is lux / second.

[0156] : Time variable, assuming that the data is collected at the 10th second.

[0157] p: Environmental factor, taking into account factors such as temperature and humidity, assumed to be 0.3.

[0158] cs: The value of the camera setting, assumed to be 5 (generally related to resolution and aperture size).

[0159] ext: exposure time, assumed to be 2 seconds.

[0160] Substitute into the formula and calculate:

[0161]

[0162]

[0163] The image data value collected at the 10th second is 1212.3. This value reflects the intensity of the image data captured under specific camera settings and environmental factors, which helps in the subsequent analysis of the image quality.

[0164] : The average value of the image data points, assuming .

[0165] : The number of pixels, assuming there are 10 data points.

[0166] Substituting into the formula, we get:

[0167]

[0168]

[0169] The quality characteristic value is , indicating that under the given image acquisition environment and parameters, the image deviation is small and the image quality can be considered good.

[0170] : The reference value of the current spraying parameter, assumed to be 50.

[0171] : Quality characteristic value, ,but .

[0172] : Acoustic diagnosis result, assumed to be 4.

[0173] : Adjustment coefficient, assumed to be 0.1.

[0174] Substitute into the formula and calculate:

[0175]

[0176]

[0177] The new reference value of the spraying parameters is 49.875, indicating that minor adjustments are made based on the image and acoustic analysis results to optimize the spraying effect.

[0178] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent control system for a paint spraying process, characterized in that: The system comprises: The airflow dynamic monitoring module monitors the air flow speed and direction in the spraying environment, collects the distribution information of paint particles in the air, calculates the paint particle distribution density in the spraying area based on the collected information, analyzes the paint particle behavior, and constructs a paint particle spraying density distribution map; The entropy value optimization control module analyzes the current state of the nozzle and adjusts the paint flow rate according to the paint particle spraying density distribution map, adjusts the spraying path according to the analysis results, corrects the nozzle angle and flow rate, calculates the spraying efficiency, and generates optimized spraying parameters; The acoustic quality monitoring module controls the nozzle by optimizing the spraying parameters, collects the acoustic wave signal during the spraying process, analyzes the change of the acoustic wave signal, analyzes the thickness and uniformity of the paint coating according to the analysis results, performs quality assessment, and generates acoustic diagnosis results; The visual precision correction module uses a camera to collect images of the coating after spraying, adjusts the spraying parameters in combination with the acoustic diagnosis results to correct deviations, updates the spraying strategy in real time, and generates an intelligent control solution for the paint spraying process.

2. The intelligent control system for paint spraying process according to claim 1 is characterized in that: The steps for collecting the distribution information of the paint particles in the air are: Sensors are deployed at key locations in the spraying area to record the air flow speed and direction in real time, using the air flow rate calculation formula. ； Generates a real-time record of airflow speed and direction, where Indicates the air velocity, Indicates the distance the airflow moves. Indicates time, Represents the adjustment coefficient, which is used to adjust the periodic fluctuations of air flow. represents the angular frequency, which represents the rate of periodic fluctuations, represents the phase, which indicates the initial angle of the periodic fluctuation; Based on the real-time recording of the airflow speed and direction, the data is analyzed to calculate the vectorized airflow speed and direction, using the formula, ； Generates vectorized airflow velocity and direction analysis data, where represents the air flow velocity vector, and are the velocity components of the airflow in the horizontal and vertical directions, and are the attenuation coefficient and time constant, which are used to enhance the model's ability to describe unsteady airflow; Using the analysis data of the vectorized air flow velocity and direction, the distribution information of paint particles in the spraying environment is collected and analyzed, and the formula is applied. ； Calculate the paint particle concentration in any area and generate paint particle air distribution information, where: Indicates at location The paint particle concentration, is the Dirac delta function, which means that at position The response when there are paint particles, It is The position of each paint particle, is the total volume area.

3. The intelligent control system for paint spraying process according to claim 2 is characterized in that: The steps for constructing the paint particle spraying density distribution map are as follows: According to the air distribution information of the paint particles, statistical analysis is performed to calculate the distribution density of the paint particles in the spraying area, and the density estimation formula is used. ； Generates paint particle density analysis data, where represents the particle density, represents the Gaussian kernel function, Indicates The position of each paint particle, represents the bandwidth of the kernel function, represents the total number of particles; Based on the paint particle density analysis data, particle behavior simulation is performed using a simulation formula. ； Generate particle behavior simulation results, where is the net force acting on the particle, is the mass of the particle, is the acceleration of the particle, is the damping coefficient, which is used to adjust the effect of air resistance on the movement of paint particles. In combination with the particle behavior simulation results, data visualization technology is used to draw a paint particle distribution map, and the difference density areas are represented by color depth, and the paint particle spraying density distribution map is output.

4. The intelligent control system for paint spraying process according to claim 3 is characterized in that: The steps of analyzing the current state of the nozzle and adjusting the paint flow are as follows: According to the paint particle spraying density distribution diagram, the mean value of the regional density is calculated using the formula: ； Get the average density data, where It is The density value of the area, It is The weight coefficient of the region represents the size or importance of the region. Indicates the total number of regions, represents the weighted average density; Based on the average density data, calculate the standard deviation to assess the current uniformity of the nozzle using the formula, ； Generate density deviation data to reflect the uniformity of the spraying process, where represents the weighted density deviation, Indicates The density value of the area, represents the weighted average density, It is The weight coefficient of the region, Indicates the total number of regions; Using the density deviation data, adjust the paint flow rate using the formula, ； The adjusted paint flow data is calculated, where: represents the adjusted paint flow, Represents the basic flow, represents the weighted density deviation, represents the base density deviation, Represents the sensitivity adjustment factor, which is used to optimize the accuracy of the calculation. represents the natural exponential function.

5. The intelligent control system for paint spraying process according to claim 4 is characterized in that: The steps for obtaining the optimized spraying parameters are: According to the adjusted paint flow data, calculate the basic flow The difference between ； Generate traffic difference data, where Represents the difference in flow before and after. represents the adjusted paint flow, Represents basic traffic; Based on the flow difference data, the nozzle angle is adjusted to match the new flow demand, using the formula, ； Generate new nozzle angle parameters, where represents the new nozzle angle, represents the original nozzle angle, represents the angle adjustment factor, which is used to adjust the sensitivity of nozzle angle changes; According to the new nozzle angle parameters and the adjusted paint flow data, the formula is used: ； Calculate the expected spraying efficiency and output the optimized spraying parameters, where: Represents the adjusted spraying efficiency, Represents the adjusted traffic data, represents the new nozzle angle parameter, Represents the estimated spraying area.

6. The paint spraying process intelligent control system according to claim 5 is characterized by: The analysis steps of the acoustic wave signal change are: According to the optimized spraying parameters, combined with the actual conditions, adjust the operating parameters of the nozzle, using the formula, ； Generate adjusted nozzle control parameters; where, and They are demand and current spray flow, Indicates the deviation from the target pressure, is the target pressure, is the adjustment index, which is used to enhance the sensitivity of the adjustment process. Represents optimized spraying parameters; Based on the adjusted nozzle control parameters, a microphone is used to collect the acoustic wave signal, and the formula is used: ； Perform signal processing to generate sound wave signal analysis results, where: and are the time-dependent amplitude and phase changes, respectively, is the fundamental frequency, is a random noise term, A time series representing an acoustic signal; According to the acoustic signal analysis results, a deep analysis is performed using the formula: ； Analyze the key features in the spectrum, calculate the spectrum distribution, and obtain the analysis results of the sound wave signal changes, among which, represents the frequency spectrum of the sound wave signal, Represents the angular frequency.

7. The paint spraying process intelligent control system according to claim 6 is characterized by: The steps for obtaining the acoustic diagnosis result are: Based on the analysis results of the acoustic wave signal changes, the coating thickness is calculated using the formula: ； Output coating thickness data, where is the material attenuation coefficient, is the maximum amplitude of the spectrum, is the reference amplitude, is the calibration constant, Indicates the coating thickness value; The coating thickness data was analyzed and the statistical distribution was evaluated using the formula, ； Calculate the coating uniformity and obtain the coating uniformity analysis results, where: Indicates the coating uniformity evaluation value, Indicates the coating thickness at the measuring point, represents the average coating thickness, Indicates the number of measurement points; The coating uniformity analysis results were compared with industry standards for quality assessment using the formula, ； Generate acoustic diagnostic results ,in, is the quality rating coefficient, is the maximum allowable uniformity value.

8. The intelligent control system for paint spraying process according to claim 7 is characterized in that: The steps for obtaining the intelligent control scheme of the paint spraying process are as follows: The camera is used to capture the coating image after spraying in real time, and the enhanced image acquisition formula is used. ； Generate a preliminary coating image dataset, where Representative time The image data at that time, cs represents the camera setting parameter value, represents exposure time, L represents lighting intensity, and p represents environmental factors. is a normalization constant to ensure the rationality of the data; Apply deep learning image analysis techniques to the preliminary coating image dataset to extract key features of coating quality, using the formula, ； Get the coating quality feature set, where is the average value of the image data, is the total number of pixels, Represents the image quality characteristic value; Based on the coating quality feature set and acoustic diagnosis results, the spraying parameters are dynamically adjusted, and the formula is applied. ； Generate feedback-adjusted spray parameters, where Represents the reference value of the new spraying parameters, is the reference value of the current spraying parameters, Indicates the acoustic diagnosis result, is the adjustment factor used to enhance the calculation accuracy; Apply the feedback-adjusted spraying parameters, continuously monitor the spraying effect, integrate all monitoring data, update the spraying strategy, and output an intelligent control solution for the paint spraying process.

Images